mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-20 23:58:12 +00:00
DiffSynth-Studio 2.0 major update
This commit is contained in:
root
@@ -3,7 +3,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--dataset_metadata_path data/example_image_dataset/metadata.csv \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 200 \
|
||||
--model_id_with_origin_paths "ostris/Flex.2-preview:Flex.2-preview.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "ostris/Flex.2-preview:Flex.2-preview.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--data_file_keys "image,kontext_images" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Kontext-dev:flux1-kontext-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Kontext-dev:flux1-kontext-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -3,7 +3,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--dataset_metadata_path data/example_image_dataset/metadata.csv \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/AttriCtrl-FLUX.1-Dev:models/brightness.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/AttriCtrl-FLUX.1-Dev:models/brightness.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.value_controller.encoders.0." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--data_file_keys "image,controlnet_image,controlnet_inpaint_mask" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta:diffusion_pytorch_model.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta:diffusion_pytorch_model.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.controlnet.models.0." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--data_file_keys "image,controlnet_image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-Controlnet-Union-alpha:diffusion_pytorch_model.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-Controlnet-Union-alpha:diffusion_pytorch_model.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.controlnet.models.0." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--data_file_keys "image,controlnet_image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,jasperai/Flux.1-dev-Controlnet-Upscaler:diffusion_pytorch_model.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,jasperai/Flux.1-dev-Controlnet-Upscaler:diffusion_pytorch_model.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.controlnet.models.0." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,ipadapter_images" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-IP-Adapter:ip-adapter.bin,google/siglip-so400m-patch14-384:" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-IP-Adapter:ip-adapter.bin,google/siglip-so400m-patch14-384:model.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.ipadapter." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--data_file_keys "image,controlnet_image,infinityou_id_image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/image_proj_model.bin,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/image_proj_model.bin,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev:model.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev:model.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.lora_encoder." \
|
||||
|
||||
@@ -3,7 +3,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--dataset_metadata_path data/example_image_dataset/metadata.csv \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--data_file_keys "image,nexus_gen_reference_image" \
|
||||
--max_pixels 262144 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/Nexus-GenV2:model*.safetensors,DiffSynth-Studio/Nexus-GenV2:edit_decoder.bin,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/Nexus-GenV2:model*.safetensors,DiffSynth-Studio/Nexus-GenV2:edit_decoder.bin,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
|
||||
--data_file_keys "image,step1x_reference_image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "Qwen/Qwen2.5-VL-7B-Instruct:,stepfun-ai/Step1X-Edit:step1x-edit-i1258.safetensors,stepfun-ai/Step1X-Edit:vae.safetensors" \
|
||||
--model_id_with_origin_paths "Qwen/Qwen2.5-VL-7B-Instruct:model-*.safetensors,stepfun-ai/Step1X-Edit:step1x-edit-i1258.safetensors,stepfun-ai/Step1X-Edit:vae.safetensors" \
|
||||
--learning_rate 1e-5 \
|
||||
--num_epochs 1 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -3,7 +3,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--dataset_metadata_path data/example_image_dataset/metadata.csv \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 50 \
|
||||
--model_id_with_origin_paths "ostris/Flex.2-preview:Flex.2-preview.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "ostris/Flex.2-preview:Flex.2-preview.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,kontext_images" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Kontext-dev:flux1-kontext-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Kontext-dev:flux1-kontext-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -3,7 +3,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--dataset_metadata_path data/example_image_dataset/metadata.csv \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 50 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/AttriCtrl-FLUX.1-Dev:models/brightness.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/AttriCtrl-FLUX.1-Dev:models/brightness.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,controlnet_image,controlnet_inpaint_mask" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta:diffusion_pytorch_model.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta:diffusion_pytorch_model.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,controlnet_image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-Controlnet-Union-alpha:diffusion_pytorch_model.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-Controlnet-Union-alpha:diffusion_pytorch_model.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,controlnet_image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,jasperai/Flux.1-dev-Controlnet-Upscaler:diffusion_pytorch_model.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,jasperai/Flux.1-dev-Controlnet-Upscaler:diffusion_pytorch_model.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,eligen_entity_masks" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 50 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,ipadapter_images" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 50 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-IP-Adapter:ip-adapter.bin,google/siglip-so400m-patch14-384:" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-IP-Adapter:ip-adapter.bin,google/siglip-so400m-patch14-384:model.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,controlnet_image,infinityou_id_image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 100 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/image_proj_model.bin,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/image_proj_model.bin,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -3,7 +3,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--dataset_metadata_path data/example_image_dataset/metadata.csv \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 50 \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,nexus_gen_reference_image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 400 \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/Nexus-GenV2:model*.safetensors,DiffSynth-Studio/Nexus-GenV2:edit_decoder.bin,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--model_id_with_origin_paths "DiffSynth-Studio/Nexus-GenV2:model*.safetensors,DiffSynth-Studio/Nexus-GenV2:edit_decoder.bin,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
|
||||
--data_file_keys "image,step1x_reference_image" \
|
||||
--max_pixels 1048576 \
|
||||
--dataset_repeat 50 \
|
||||
--model_id_with_origin_paths "Qwen/Qwen2.5-VL-7B-Instruct:,stepfun-ai/Step1X-Edit:step1x-edit-i1258.safetensors,stepfun-ai/Step1X-Edit:vae.safetensors" \
|
||||
--model_id_with_origin_paths "Qwen/Qwen2.5-VL-7B-Instruct:model-*.safetensors,stepfun-ai/Step1X-Edit:step1x-edit-i1258.safetensors,stepfun-ai/Step1X-Edit:vae.safetensors" \
|
||||
--learning_rate 1e-4 \
|
||||
--num_epochs 5 \
|
||||
--remove_prefix_in_ckpt "pipe.dit." \
|
||||
|
||||
@@ -1,47 +1,60 @@
|
||||
import torch, os, json
|
||||
from diffsynth import load_state_dict
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth.trainers.utils import DiffusionTrainingModule, ModelLogger, launch_training_task, flux_parser
|
||||
from diffsynth.models.lora import FluxLoRAConverter
|
||||
from diffsynth.trainers.unified_dataset import UnifiedDataset
|
||||
import torch, os, argparse, accelerate
|
||||
from diffsynth.core import UnifiedDataset
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.diffusion import *
|
||||
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
||||
|
||||
|
||||
|
||||
class FluxTrainingModule(DiffusionTrainingModule):
|
||||
def __init__(
|
||||
self,
|
||||
model_paths=None, model_id_with_origin_paths=None,
|
||||
tokenizer_1_path=None, tokenizer_2_path=None,
|
||||
trainable_models=None,
|
||||
lora_base_model=None, lora_target_modules="a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp", lora_rank=32, lora_checkpoint=None,
|
||||
lora_base_model=None, lora_target_modules="", lora_rank=32, lora_checkpoint=None,
|
||||
preset_lora_path=None, preset_lora_model=None,
|
||||
use_gradient_checkpointing=True,
|
||||
use_gradient_checkpointing_offload=False,
|
||||
extra_inputs=None,
|
||||
fp8_models=None,
|
||||
offload_models=None,
|
||||
device="cpu",
|
||||
task="sft",
|
||||
):
|
||||
super().__init__()
|
||||
# Load models
|
||||
model_configs = self.parse_model_configs(model_paths, model_id_with_origin_paths, enable_fp8_training=False)
|
||||
self.pipe = FluxImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device="cpu", model_configs=model_configs)
|
||||
|
||||
model_configs = self.parse_model_configs(model_paths, model_id_with_origin_paths, fp8_models=fp8_models, offload_models=offload_models, device=device)
|
||||
tokenizer_1_config = ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="tokenizer/") if tokenizer_1_path is None else ModelConfig(tokenizer_1_path)
|
||||
tokenizer_2_config = ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="tokenizer_2/") if tokenizer_2_path is None else ModelConfig(tokenizer_2_path)
|
||||
self.pipe = FluxImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device=device, model_configs=model_configs, tokenizer_1_config=tokenizer_1_config, tokenizer_2_config=tokenizer_2_config)
|
||||
self.pipe = self.split_pipeline_units(task, self.pipe, trainable_models, lora_base_model)
|
||||
|
||||
# Training mode
|
||||
self.switch_pipe_to_training_mode(
|
||||
self.pipe, trainable_models,
|
||||
lora_base_model, lora_target_modules, lora_rank, lora_checkpoint=lora_checkpoint,
|
||||
enable_fp8_training=False,
|
||||
lora_base_model, lora_target_modules, lora_rank, lora_checkpoint,
|
||||
preset_lora_path, preset_lora_model,
|
||||
task=task,
|
||||
)
|
||||
|
||||
# Store other configs
|
||||
# Other configs
|
||||
self.use_gradient_checkpointing = use_gradient_checkpointing
|
||||
self.use_gradient_checkpointing_offload = use_gradient_checkpointing_offload
|
||||
self.extra_inputs = extra_inputs.split(",") if extra_inputs is not None else []
|
||||
self.fp8_models = fp8_models
|
||||
self.task = task
|
||||
self.task_to_loss = {
|
||||
"sft:data_process": lambda pipe, *args: args,
|
||||
"direct_distill:data_process": lambda pipe, *args: args,
|
||||
"sft": lambda pipe, inputs_shared, inputs_posi, inputs_nega: FlowMatchSFTLoss(pipe, **inputs_shared, **inputs_posi),
|
||||
"sft:train": lambda pipe, inputs_shared, inputs_posi, inputs_nega: FlowMatchSFTLoss(pipe, **inputs_shared, **inputs_posi),
|
||||
"direct_distill": lambda pipe, inputs_shared, inputs_posi, inputs_nega: DirectDistillLoss(pipe, **inputs_shared, **inputs_posi),
|
||||
"direct_distill:train": lambda pipe, inputs_shared, inputs_posi, inputs_nega: DirectDistillLoss(pipe, **inputs_shared, **inputs_posi),
|
||||
}
|
||||
|
||||
|
||||
def forward_preprocess(self, data):
|
||||
# CFG-sensitive parameters
|
||||
def get_pipeline_inputs(self, data):
|
||||
inputs_posi = {"prompt": data["prompt"]}
|
||||
inputs_nega = {"negative_prompt": ""}
|
||||
|
||||
# CFG-unsensitive parameters
|
||||
inputs_shared = {
|
||||
# Assume you are using this pipeline for inference,
|
||||
# please fill in the input parameters.
|
||||
@@ -58,34 +71,78 @@ class FluxTrainingModule(DiffusionTrainingModule):
|
||||
"use_gradient_checkpointing": self.use_gradient_checkpointing,
|
||||
"use_gradient_checkpointing_offload": self.use_gradient_checkpointing_offload,
|
||||
}
|
||||
|
||||
# Extra inputs
|
||||
controlnet_input = {}
|
||||
for extra_input in self.extra_inputs:
|
||||
if extra_input.startswith("controlnet_"):
|
||||
controlnet_input[extra_input.replace("controlnet_", "")] = data[extra_input]
|
||||
else:
|
||||
inputs_shared[extra_input] = data[extra_input]
|
||||
if len(controlnet_input) > 0:
|
||||
inputs_shared["controlnet_inputs"] = [ControlNetInput(**controlnet_input)]
|
||||
|
||||
# Pipeline units will automatically process the input parameters.
|
||||
for unit in self.pipe.units:
|
||||
inputs_shared, inputs_posi, inputs_nega = self.pipe.unit_runner(unit, self.pipe, inputs_shared, inputs_posi, inputs_nega)
|
||||
return {**inputs_shared, **inputs_posi}
|
||||
|
||||
inputs_shared = self.parse_extra_inputs(data, self.extra_inputs, inputs_shared)
|
||||
return inputs_shared, inputs_posi, inputs_nega
|
||||
|
||||
def forward(self, data, inputs=None):
|
||||
if inputs is None: inputs = self.forward_preprocess(data)
|
||||
models = {name: getattr(self.pipe, name) for name in self.pipe.in_iteration_models}
|
||||
loss = self.pipe.training_loss(**models, **inputs)
|
||||
if inputs is None: inputs = self.get_pipeline_inputs(data)
|
||||
inputs = self.transfer_data_to_device(inputs, self.pipe.device, self.pipe.torch_dtype)
|
||||
for unit in self.pipe.units:
|
||||
inputs = self.pipe.unit_runner(unit, self.pipe, *inputs)
|
||||
loss = self.task_to_loss[self.task](self.pipe, *inputs)
|
||||
return loss
|
||||
|
||||
|
||||
def flux_parser():
|
||||
parser = argparse.ArgumentParser(description="Simple example of a training script.")
|
||||
parser = add_general_config(parser)
|
||||
parser = add_image_size_config(parser)
|
||||
parser.add_argument("--tokenizer_1_path", type=str, default=None, help="Path to CLIP tokenizer.")
|
||||
parser.add_argument("--tokenizer_2_path", type=str, default=None, help="Path to T5 tokenizer.")
|
||||
parser.add_argument("--align_to_opensource_format", default=False, action="store_true", help="Whether to align the lora format to opensource format. Only for DiT's LoRA.")
|
||||
return parser
|
||||
|
||||
|
||||
def convert_lora_format(state_dict, alpha=None):
|
||||
prefix_rename_dict = {
|
||||
"single_blocks": "lora_unet_single_blocks",
|
||||
"blocks": "lora_unet_double_blocks",
|
||||
}
|
||||
middle_rename_dict = {
|
||||
"norm.linear": "modulation_lin",
|
||||
"to_qkv_mlp": "linear1",
|
||||
"proj_out": "linear2",
|
||||
"norm1_a.linear": "img_mod_lin",
|
||||
"norm1_b.linear": "txt_mod_lin",
|
||||
"attn.a_to_qkv": "img_attn_qkv",
|
||||
"attn.b_to_qkv": "txt_attn_qkv",
|
||||
"attn.a_to_out": "img_attn_proj",
|
||||
"attn.b_to_out": "txt_attn_proj",
|
||||
"ff_a.0": "img_mlp_0",
|
||||
"ff_a.2": "img_mlp_2",
|
||||
"ff_b.0": "txt_mlp_0",
|
||||
"ff_b.2": "txt_mlp_2",
|
||||
}
|
||||
suffix_rename_dict = {
|
||||
"lora_B.weight": "lora_up.weight",
|
||||
"lora_A.weight": "lora_down.weight",
|
||||
}
|
||||
state_dict_ = {}
|
||||
for name, param in state_dict.items():
|
||||
names = name.split(".")
|
||||
if names[-2] != "lora_A" and names[-2] != "lora_B":
|
||||
names.pop(-2)
|
||||
prefix = names[0]
|
||||
middle = ".".join(names[2:-2])
|
||||
suffix = ".".join(names[-2:])
|
||||
block_id = names[1]
|
||||
if middle not in middle_rename_dict:
|
||||
continue
|
||||
rename = prefix_rename_dict[prefix] + "_" + block_id + "_" + middle_rename_dict[middle] + "." + suffix_rename_dict[suffix]
|
||||
state_dict_[rename] = param
|
||||
if rename.endswith("lora_up.weight"):
|
||||
lora_alpha = alpha if alpha is not None else param.shape[-1]
|
||||
state_dict_[rename.replace("lora_up.weight", "alpha")] = torch.tensor((lora_alpha,))[0]
|
||||
return state_dict_
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = flux_parser()
|
||||
args = parser.parse_args()
|
||||
accelerator = accelerate.Accelerator(
|
||||
gradient_accumulation_steps=args.gradient_accumulation_steps,
|
||||
kwargs_handlers=[accelerate.DistributedDataParallelKwargs(find_unused_parameters=args.find_unused_parameters)],
|
||||
)
|
||||
dataset = UnifiedDataset(
|
||||
base_path=args.dataset_base_path,
|
||||
metadata_path=args.dataset_metadata_path,
|
||||
@@ -103,18 +160,34 @@ if __name__ == "__main__":
|
||||
model = FluxTrainingModule(
|
||||
model_paths=args.model_paths,
|
||||
model_id_with_origin_paths=args.model_id_with_origin_paths,
|
||||
tokenizer_1_path=args.tokenizer_1_path,
|
||||
tokenizer_2_path=args.tokenizer_2_path,
|
||||
trainable_models=args.trainable_models,
|
||||
lora_base_model=args.lora_base_model,
|
||||
lora_target_modules=args.lora_target_modules,
|
||||
lora_rank=args.lora_rank,
|
||||
lora_checkpoint=args.lora_checkpoint,
|
||||
preset_lora_path=args.preset_lora_path,
|
||||
preset_lora_model=args.preset_lora_model,
|
||||
use_gradient_checkpointing=args.use_gradient_checkpointing,
|
||||
use_gradient_checkpointing_offload=args.use_gradient_checkpointing_offload,
|
||||
extra_inputs=args.extra_inputs,
|
||||
fp8_models=args.fp8_models,
|
||||
offload_models=args.offload_models,
|
||||
task=args.task,
|
||||
device=accelerator.device,
|
||||
)
|
||||
model_logger = ModelLogger(
|
||||
args.output_path,
|
||||
remove_prefix_in_ckpt=args.remove_prefix_in_ckpt,
|
||||
state_dict_converter=FluxLoRAConverter.align_to_opensource_format if args.align_to_opensource_format else lambda x:x,
|
||||
state_dict_converter=convert_lora_format if args.align_to_opensource_format else lambda x:x,
|
||||
)
|
||||
launch_training_task(dataset, model, model_logger, args=args)
|
||||
launcher_map = {
|
||||
"sft:data_process": launch_data_process_task,
|
||||
"direct_distill:data_process": launch_data_process_task,
|
||||
"sft": launch_training_task,
|
||||
"sft:train": launch_training_task,
|
||||
"direct_distill": launch_training_task,
|
||||
"direct_distill:train": launch_training_task,
|
||||
}
|
||||
launcher_map[args.task](accelerator, dataset, model, model_logger, args=args)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth import load_state_dict
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="ostris/Flex.2-preview", origin_file_pattern="Flex.2-preview.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth import load_state_dict
|
||||
from PIL import Image
|
||||
|
||||
@@ -10,7 +10,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-Kontext-dev", origin_file_pattern="flux1-kontext-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth import load_state_dict
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-Krea-dev", origin_file_pattern="flux1-krea-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth import load_state_dict
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/brightness.safetensors")
|
||||
],
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth import load_state_dict
|
||||
from PIL import Image
|
||||
|
||||
@@ -10,7 +10,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", origin_file_pattern="diffusion_pytorch_model.safetensors"),
|
||||
],
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth import load_state_dict
|
||||
from PIL import Image
|
||||
|
||||
@@ -10,7 +10,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="InstantX/FLUX.1-dev-Controlnet-Union-alpha", origin_file_pattern="diffusion_pytorch_model.safetensors"),
|
||||
],
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth import load_state_dict
|
||||
from PIL import Image
|
||||
|
||||
@@ -10,7 +10,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="jasperai/Flux.1-dev-Controlnet-Upscaler", origin_file_pattern="diffusion_pytorch_model.safetensors"),
|
||||
],
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth import load_state_dict
|
||||
from PIL import Image
|
||||
|
||||
@@ -10,10 +10,10 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="InstantX/FLUX.1-dev-IP-Adapter", origin_file_pattern="ip-adapter.bin"),
|
||||
ModelConfig(model_id="google/siglip-so400m-patch14-384"),
|
||||
ModelConfig(model_id="google/siglip-so400m-patch14-384", origin_file_pattern="model.safetensors"),
|
||||
],
|
||||
)
|
||||
state_dict = load_state_dict("models/train/FLUX.1-dev-IP-Adapter_full/epoch-0.safetensors")
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth import load_state_dict
|
||||
from PIL import Image
|
||||
|
||||
@@ -10,7 +10,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/image_proj_model.bin"),
|
||||
ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors"),
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth import load_state_dict
|
||||
|
||||
|
||||
@@ -9,17 +9,16 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev", origin_file_pattern="model.safetensors"),
|
||||
],
|
||||
)
|
||||
pipe.enable_lora_magic()
|
||||
state_dict = load_state_dict("models/train/FLUX.1-dev-LoRA-Encoder_full/epoch-0.safetensors")
|
||||
pipe.lora_encoder.load_state_dict(state_dict)
|
||||
|
||||
lora = ModelConfig(model_id="VoidOc/flux_animal_forest1", origin_file_pattern="20.safetensors")
|
||||
pipe.load_lora(pipe.dit, lora, hotload=True) # Use `pipe.clear_lora()` to drop the loaded LoRA.
|
||||
pipe.load_lora(pipe.dit, lora) # Use `pipe.clear_lora()` to drop the loaded LoRA.
|
||||
|
||||
image = pipe(prompt="", seed=0, lora_encoder_inputs=lora)
|
||||
image.save("image_FLUX.1-dev-LoRA-Encoder_full.jpg")
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth import load_state_dict
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from PIL import Image
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth import load_state_dict
|
||||
|
||||
pipe = FluxImagePipeline.from_pretrained(
|
||||
@@ -10,7 +10,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="model*.safetensors"),
|
||||
ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="edit_decoder.bin"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from diffsynth import load_state_dict
|
||||
from PIL import Image
|
||||
|
||||
@@ -8,7 +8,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
torch_dtype=torch.bfloat16,
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="Qwen/Qwen2.5-VL-7B-Instruct"),
|
||||
ModelConfig(model_id="Qwen/Qwen2.5-VL-7B-Instruct", origin_file_pattern="model-*.safetensors"),
|
||||
ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="step1x-edit-i1258.safetensors"),
|
||||
ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="vae.safetensors"),
|
||||
],
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
|
||||
|
||||
pipe = FluxImagePipeline.from_pretrained(
|
||||
@@ -8,7 +8,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="ostris/Flex.2-preview", origin_file_pattern="Flex.2-preview.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from PIL import Image
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-Kontext-dev", origin_file_pattern="flux1-kontext-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
|
||||
|
||||
pipe = FluxImagePipeline.from_pretrained(
|
||||
@@ -8,7 +8,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-Krea-dev", origin_file_pattern="flux1-krea-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
|
||||
|
||||
pipe = FluxImagePipeline.from_pretrained(
|
||||
@@ -8,7 +8,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/brightness.safetensors")
|
||||
],
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from PIL import Image
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", origin_file_pattern="diffusion_pytorch_model.safetensors"),
|
||||
],
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from PIL import Image
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="InstantX/FLUX.1-dev-Controlnet-Union-alpha", origin_file_pattern="diffusion_pytorch_model.safetensors"),
|
||||
],
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from PIL import Image
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="jasperai/Flux.1-dev-Controlnet-Upscaler", origin_file_pattern="diffusion_pytorch_model.safetensors"),
|
||||
],
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from PIL import Image
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
|
||||
pipe = FluxImagePipeline.from_pretrained(
|
||||
torch_dtype=torch.bfloat16,
|
||||
@@ -8,7 +8,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from PIL import Image
|
||||
|
||||
|
||||
@@ -9,10 +9,10 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="InstantX/FLUX.1-dev-IP-Adapter", origin_file_pattern="ip-adapter.bin"),
|
||||
ModelConfig(model_id="google/siglip-so400m-patch14-384"),
|
||||
ModelConfig(model_id="google/siglip-so400m-patch14-384", origin_file_pattern="model.safetensors"),
|
||||
],
|
||||
)
|
||||
pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev-IP-Adapter_lora/epoch-4.safetensors", alpha=1)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
|
||||
from PIL import Image
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/image_proj_model.bin"),
|
||||
ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors"),
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
|
||||
|
||||
pipe = FluxImagePipeline.from_pretrained(
|
||||
@@ -8,7 +8,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
model_configs=[
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import torch
|
||||
from PIL import Image
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
|
||||
pipe = FluxImagePipeline.from_pretrained(
|
||||
torch_dtype=torch.bfloat16,
|
||||
@@ -9,7 +9,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="model*.safetensors"),
|
||||
ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="edit_decoder.bin"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
|
||||
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
|
||||
],
|
||||
)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import torch
|
||||
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
|
||||
from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
|
||||
from PIL import Image
|
||||
|
||||
|
||||
@@ -7,7 +7,7 @@ pipe = FluxImagePipeline.from_pretrained(
|
||||
torch_dtype=torch.bfloat16,
|
||||
device="cuda",
|
||||
model_configs=[
|
||||
ModelConfig(model_id="Qwen/Qwen2.5-VL-7B-Instruct"),
|
||||
ModelConfig(model_id="Qwen/Qwen2.5-VL-7B-Instruct", origin_file_pattern="model-*.safetensors"),
|
||||
ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="step1x-edit-i1258.safetensors"),
|
||||
ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="vae.safetensors"),
|
||||
],
|
||||
|
||||
Reference in New Issue
Block a user